Agents & workloads
9 articles in Agents & workloadsSearch all articles
Articles
6 October 2026
Multi-step agent workloads: latency and cost budgets
An AI agent makes many calls in a row, so one task can easily take half a minute and cost several cents. This guide shows how to give each task a time and cost limit and stay inside it: measure how many steps tasks really take, run independent tool calls in parallel, and stop at a step cap. In our worked example, that brought the slowest tasks from 34.9 to 28.1 seconds without changing the model. On Lyceum each step is billed per token, so the budget translates directly into your bill.
30 September 2026
RAG pipeline GPU sizing: cost per query, end to end
One question to a retrieval-augmented generation (RAG) assistant costs almost exactly its answer step. In our example, that is $0.00277 per query on our API, and two thirds of it pays for the retrieved text. On a GPU you rent, the same query costs between $0.0007 and $0.009, depending on how many queries share the GPU at once.
10 September 2026
AI dubbing costs: GPU pipelines vs commercial APIs
Dubbing as one API costs $2.20 per minute on ElevenLabs Dubbing v2, read on 30 October 2026. Bought stage by stage, transcription, translation and the synthetic voice cost about $0.10 per minute in our example. The extra $2.10 pays for automation: detecting speakers, keeping their voices and fitting the new speech into the video. On Lyceum you can run translation and transcription yourself in European data centres: translation on our API, with prompts and outputs not stored, and transcription as a GPU batch job billed only while it runs.
9 September 2026
Running Wan 2.2 on cloud GPU: VRAM needs & cost per clip
Wan 2.2's large video model, with 14 billion parameters, needs a GPU with 80 GB of memory to render 720p clips. On one NVIDIA H100, a five-second 720p clip took the Wan team 1,041.5 seconds. At our on-demand H100 price, that comes to about $1.36 per clip.
7 September 2026
GPU cost for batch vision inference: DINOv3, SAM & CLIP
Running DINOv3, SAM or CLIP over millions of images gets expensive when the GPU sits idle, waiting for the CPU to decode and resize the next images. You pay for every GPU hour, busy or not. So before you rent a bigger GPU, check whether yours is waiting, and speed up image loading first. On Lyceum you rent GPU machines by the second, and spot machines cost about half as much, which suits a batch job that can restart.
6 June 2026
Tool calling latency in LLM inference: production optimization
When your agent calls a tool, users can wait seconds before anything happens, even though the tool itself answers in milliseconds. The delay is the model: it often writes a long reasoning text first, reads a long list of tool descriptions, or gets the call wrong and has to try again. Fix it by switching reasoning off for simple calls, keeping tool descriptions short and at the start of the prompt, and forcing a valid call. On Lyceum, Qwen3.8 27B runs with or without reasoning, both with tool calling, and repeated prompt starts are cached automatically at a lower price.
5 June 2026
RAG pipeline GPU infrastructure: the engineering guide
Many teams price a RAG pipeline as one big GPU job and buy too much hardware. Only one of its four steps, writing the answer, needs large GPUs, and it drives almost all of the cost. Search can run on ordinary CPU servers, and the cheapest saving is to send fewer retrieved passages to the model. On Lyceum you call both the embedding model and the answer model per token through one API in Paris and Finland, so you pay for questions answered, not for idle GPUs.
3 June 2026
EU Compliant AI Agent Infrastructure: The 2026 Engineering Guide
EU customers ask two things before they buy an AI agent: where does each model call run, and what is kept? An agent makes many calls per task and resends its growing history each time, so cost and memory add up quickly. Run the model in Europe with a provider that stores no prompts, budget per step, and write your own log of every step, because the provider has none to give you. On Lyceum, models run in Paris and Finland, and we keep only a usage record with token counts, never your prompts or outputs.
30 May 2026
Deploy Whisper Large v3 GPU API: VRAM, performance & EU hosting
If you need to transcribe a lot of audio, running Whisper Large v3 yourself costs about 4 cents per audio hour in our example. The usual mistake is to pick the GPU by memory: Whisper fits on almost any GPU, so what decides the cost is how much audio one GPU transcribes per hour. Measure that speed on your own audio, keep the GPU busy, and size from there. On Lyceum you can run Whisper on GPU machines in European data centres billed per second, or run a backlog as a job that stops when it is done.
No articles match.
Try a different word or topic, or clear the search.